In the field of computer vision, self-supervised learning has emerged as a method to extract robust features from unlabeled data, where models derive labels autonomously from the data itself, without the need for manual annotation. This paper provides a comprehensive review of discriminative approaches of self-supervised learning within the domain of computer vision, examining their evolution and current status. Through an exploration of various methods including contrastive, self-distillation, knowledge distillation, feature decorrelation, and clustering techniques, we investigate how these approaches leverage the abundance of unlabeled data. Finally, we have comparison of self-supervised learning methods on the standard ImageNet classification benchmark.

翻译：在计算机视觉领域，自监督学习已成为一种从无标签数据中提取鲁棒特征的方法，其中模型自主地从数据本身生成标签，无需人工标注。本文全面回顾了计算机视觉领域中自监督学习的判别式方法，探讨了其演化历程及当前现状。通过深入分析包括对比学习、自蒸馏、知识蒸馏、特征去相关和聚类技术在内的多种方法，我们研究了这些方法如何利用海量无标签数据。最后，我们在标准ImageNet分类基准上对各种自监督学习方法进行了比较。